Replay of round 13
One round of the memory arm, step by step: what it read from Walrus Memory, what it decided to buy and why, the payment on Sui, how the answer was graded, and the belief version it wrote back.
Memory arm: 2 paid answers for 0.030 USDC, 1 refusal, 0 wrong answers accepted. Blind arm, same round: 2 paid answers for 0.020 USDC, 0 wrong answers accepted.
1Read memory
Before buying anything, the agent recalls its beliefs from Walrus Memory. These are the newest version of each belief written before round 13, which is what a recall returns. The run did not log its recalls; the trace flag that prints them was added for the 2026-11-03 rerun, where the recalled versions matched the newest ones written.
Seller For Version Trust Last result Cooldown until Blob Control seller (ours) market prices v7 0.40 checked, wrong 15:44 UTC ThLEEklp…_dCESui Address Inspector address facts v10 0.72 checked, right – NRETZebS…Bu_gPipTradeDex market prices v8 0.82 bought on trust, not checked – GHHOCoXY…8tw8Control seller (ours) address facts v3 0.27 checked, wrong 15:44 UTC i5K4HiK9…IrKYAgentProof endpoint checks v3 0.21 failed, nothing delivered 16:25 UTC Nu3kUpVC…BnW8Omnia endpoint verify endpoint checks v3 0.21 dead route 16:25 UTC F_dcq_Fb…d6IAPipTradeDex swap quotes v4 0.50 bought on trust, not checked – ojCSG1eW…NqDcControl seller (ours) swap quotes v2 0.50 bought on trust, not checked – oO2zUouH…YYDQ2Decide
The trust policy is plain code over those beliefs: below the 0.6 floor a seller gets only canaries; in a cooldown it gets nothing; above the floor, the cheapest good seller wins, with spot checks that thin out as trust grows. If a checked answer fails, it tries the next seller once in the same round.
address factsSui Address Inspector independent, as a purchase with a spot check. Reason it gave: “cheapest good answer at trust 0.72”.
market pricesPipTradeDex independent, as a purchase with a spot check. Reason it gave: “cheapest good answer at trust 0.82”.
endpoint checksRefused to buy. Reason it gave: “no seller is trusted and none is due a canary”.
3Pay
Each purchase is an x402 payment in USDC on Sui mainnet. Gas price is 0: these are gasless transfers.
Sui Address Inspector independent · address facts- Paid
- 0.010 USDC
- Sui transaction
9scPcqqtcJB9XmC3vcVBnpwFsYciYbVEb2QFFcn7TJfm- Answer in
- 0.9 s
- At
- 15:36:27 UTC
PipTradeDex independent · market prices- Paid
- 0.020 USDC
- Sui transaction
CSUQFfhVojbRzsvNjwir9DyfUkSo8J86916GUHUorVoW- Answer in
- 8.0 s
- At
- 15:36:39 UTC
4Grade
Its own check compares the answer with chain truth read through Tatum: balances for address facts, the deepest native USDC/SUI pool for market prices. Answers bought on trust are not checked by the agent. The audit is the experiment's scoring, which checks every answer; the agent never sees it.
Sui Address Inspector · address facts- Its own check
- checked, right (all 6 balances matched the chain)
- The audit
- right (all 6 balances matched the chain)
PipTradeDex · market prices- Its own check
- checked, right (price within 0.12% of the reference)
- The audit
- right (price within 0.12% of the reference)
5Remember
Each purchase becomes a verdict and a new version of that seller's belief, both written to Walrus Memory. The next round starts by reading these.
Sui Address Inspector · address facts- Verdict memory
yhfmE8oL…4Dakintwiceshy-verdicts- Belief written
- v11: trust 0.72 → 0.75. passed: all 6 balances matched the chain
- Walrus blob
e1nx1gKadTtnQDa1aOiMIHcJYT6Y2XoImzJBMGtQTCEintwiceshy-belief-inspector-address-facts
PipTradeDex · market prices- Verdict memory
UAIsOrGB…sA08intwiceshy-verdicts- Belief written
- v9: trust 0.82 → 0.84. passed: price within 0.12% of the reference
- Walrus blob
P0QvaAUsuP98TK4HyTO7C52vcVsRy8iDM22VxYqnxdUintwiceshy-belief-piptradedex-market-price
The blind arm in the same round
Same market, same round, no memory and no checks: it takes the cheapest listing every time.
| For | Seller | USDC | Transaction | Audit |
|---|---|---|---|---|
| address facts | Sui Address Inspector independent | 0.010 | J1L8q3R5…fsgn | right (all 1 balances matched the chain) |
| market prices | Control seller (ours) control (ours) | 0.010 | BX8Lpmb8…Mntc | right (price within 0.01% of the reference) |
| endpoint checks | AgentProof independent | 0.000 | – | failed, nothing delivered: signed payment offered, seller returned HTTP 500, nothing settled |
| endpoint checks | Omnia endpoint verify independent | 0.000 | – | dead route: HTTP 404 before any payment |
Other rounds
Round 12, before this one. Round 14, after it. Round 7 is the first round after our control seller's fault was caught.